Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to political speeches and their impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cken
    -0.17
    -Semitism
    -0.15
    ñana
    -0.15
     Ekim
    -0.14
    zman
    -0.14
    WithEmail
    -0.14
    acters
    -0.14
    leet
    -0.14
     showModal
    -0.14
    ENTA
    -0.14
    POSITIVE LOGITS
     speech
    0.53
     address
    0.48
     Speech
    0.45
    speech
    0.45
     Address
    0.42
    Speech
    0.41
    peech
    0.40
     addresses
    0.39
    Address
    0.39
    address
    0.38
    Act Density 0.118%

    No Known Activations